Communication devices and methods for temporal analysis of voice calls

1. A headset comprising: a microphone configured to generate analog audio for a voice call; an analog-to-digital converter configured to convert the analog audio to digital audio; a voice activity detector configured to detect speech in the digital audio; a processor configured to i) determine a temporal characteristic of the speech, and ii) generate a message based on the temporal characteristic of the speech and a temporal characteristic of the voice call; and a transmitter configured to transmit the message.

2. The headset of claim 1 , wherein the voice activity detector is a first voice activity detector, wherein the audio is first audio, and wherein the speech is first speech, the headset comprising: a receiver configured to receive second digital audio; and a second voice activity detector configured to detect second speech in the second digital audio; wherein the processor is configured to determine the temporal characteristic of the voice call based on the second speech.

3. The headset of claim 2 , the processor configured to determine a parameter representing a duration of contemporaneous occurrence of the first speech and the second speech; wherein the message includes the parameter.

4. The headset of claim 2 , the processor configured to determine a parameter representing a ratio of a duration of the first speech to a duration of the second speech; wherein the message includes the parameter.

5. The headset of claim 2 , the processor configured to determine a parameter representing a duration of no speech and at least one of i) a duration of the first speech and ii) a duration of the second speech; wherein the message includes the parameter.

6. The headset of claim 2 , wherein the analog audio is first analog audio, the headset comprising: a digital-to-analog converter configured to convert the second digital audio to second analog audio; and a speaker configured to generate sound based on the second analog audio.

7. The headset of claim 2 , wherein: the processor is configured to determine amplitudes of the first speech and the second speech; and the message describes the amplitudes of the first speech and the second speech.

8. An audio adapter comprising: a headset interface configured to receive analog audio for a voice call; an analog-to-digital converter configured to convert the analog audio to digital audio; a first voice activity detector configured to detect speech in the digital audio; a processor configured to i) determine a temporal characteristic of the speech, and ii) generate a message based on the temporal characteristic of the speech and a temporal characteristic of the voice call; and a host interface configured to transmit the message.

9. The audio adapter of claim 8 , wherein the audio is first audio, and wherein the speech is first speech, the audio adapter comprising: a second voice activity detector configured to detect second speech in the second digital audio; wherein the processor is configured to determine the temporal characteristic of the voice call based on the second speech.

10. The audio adapter of claim 9 , the processor configured to determine a parameter representing a duration of contemporaneous occurrence of the first speech and the second speech; wherein the message includes the parameter.

11. The audio adapter of claim 9 , the processor configured to determine a parameter representing a ratio of a duration of the first speech to a duration of the second speech; wherein the message includes the parameter.

12. The audio adapter of claim 9 , the processor configured to determine a parameter representing a duration of no speech and at least one of i) a duration of the first speech and ii) a duration of the second speech; wherein the message includes the parameter.

13. The audio adapter of claim 9 , comprising: a digital-to-analog converter configured to convert the second digital audio to second analog audio.

14. The audio adapter of claim 9 , wherein: the processor is configured to determine amplitudes of the first speech and the second speech; and the message describes the amplitudes of the first speech and the second speech.

15. A method for a headset comprising: generating analog audio for a voice call; converting the analog audio to digital audio; detecting speech in the digital audio; determining a temporal characteristic of the speech; generating a message based on the temporal characteristic of the speech and a temporal characteristic of the voice call; and transmitting the message.

16. The method of claim 15 , wherein the audio is first audio, and wherein the speech is first speech, comprising: receiving second digital audio; detecting second speech in the second digital audio; and determining the temporal characteristic of the voice call based on the second speech.

17. The method of claim 16 , comprising: determining a parameter representing a duration of contemporaneous occurrence of the first speech and the second speech; and including the parameter in the message.

18. The method of claim 16 , comprising: determining a parameter representing a ratio of a duration of the first speech to a duration of the second speech; and including the parameter in the message.

19. The method of claim 16 , comprising: determining a parameter representing a duration of no speech and at least one of i) a duration of the first speech and ii) a duration of the second speech; and including the parameter in the message.

20. The method of claim 16 , wherein the analog audio is first analog audio, the method comprising: converting the second digital audio to second analog audio; and providing the second analog audio to a speaker of the headset.